公开(公告)号：US20250069191A1

公开(公告)日：2025-02-27

申请号：US18452634

申请日：2023-08-21

Applicant: NVIDIA Corporation

Inventor： Iuri Frosio ,  Mayoore Selvarasa Jaiswal ,  Jan Kautz ,  Jianyuan Min

IPC: G06T5/50 ,  H04N23/743

Abstract: Systems and methods are disclosed related to synthetic bracketing for exposure correction. A deep learning based method and system produces a set of differently exposed images from a single input image. The images in the set may be combined to produce an output image with improved global and local exposure compared with the input image. An image encoder applies learned parameters to each input image to generate a set of image features including local exposure estimates for each of two or more regions of the input image and a low resolution latent representation of the input image. A decoder receives the local exposure estimates, the latent representation, and target enhancements that are processed to generate synthesized transformations. When applied to the input image, the synthesized transformations produce the set of transformed images. Each transformed image is a version of the input image synthesized to correspond to a respective target enhancement.

公开(公告)号：US12088924B2

公开(公告)日：2024-09-10

申请号：US17815826

申请日：2022-07-28

Applicant: CANON KABUSHIKI KAISHA

Inventor： Takaaki Fukui

IPC: H04N23/743 ,  H04N5/33 ,  H04N23/20 ,  H04N23/56 ,  H04N23/611 ,  H04N23/617 ,  H04N23/68 ,  H04N25/58

CPC classification number: H04N23/743 ,  H04N5/33 ,  H04N23/20 ,  H04N23/56 ,  H04N23/611 ,  H04N23/617 ,  H04N23/6811 ,  H04N25/58

Abstract: A camera body includes an infrared LED that applies infrared light toward a face of a user that is a subject, and an infrared detection camera. The camera body determines a first irradiation amount of the infrared LED and a second exposure condition of the infrared detection camera in accordance with an LED OFF image acquired by capturing an image of the subject in a first exposure condition used by the infrared detection camera without the infrared light applied toward the subject, acquires the LED OFF image and acquires an image (LED ON image) of the subject irradiated with a first irradiation amount in image capture in a second exposure condition used by the infrared detection camera, and detect a face direction of the subject by using a difference image between these images.

公开(公告)号：US20240223906A1

公开(公告)日：2024-07-04

申请号：US18601406

申请日：2024-03-11

Applicant: Magic Leap, Inc.

Inventor： Brian Keith Smith ,  Ilya Tsunaev

IPC: H04N23/72 ,  H04N5/222 ,  H04N5/265 ,  H04N23/63 ,  H04N23/71 ,  H04N23/73 ,  H04N23/741 ,  H04N23/743 ,  H04N23/76

CPC classification number: H04N23/72 ,  H04N5/2226 ,  H04N5/265 ,  H04N23/71 ,  H04N23/73 ,  H04N23/741 ,  H04N23/743 ,  H04N23/76 ,  H04N23/63

Abstract: A method includes receiving a first image captured by a content capture device included in a mixed reality or augmented reality device, identifying a location corresponding to a pixel group of a plurality of pixel groups in the first image, and determining, for each location, one or more updates for one or more settings of the content capture device. The method also includes iteratively: updating the content capture device using an update of the one or more updates, capturing an image of a predetermined number of images using the content capture device and the update of the one or more updates, and repeating updating the content capture device and capturing the image the predetermined number of times. The method also includes stitching the predetermined number of images together to form a composite image.

公开(公告)号：US12003853B2

公开(公告)日：2024-06-04

申请号：US17000098

申请日：2020-08-21

Applicant: Duelight LLC

Inventor： William Guie Rivard ,  Brian J. Kindle ,  Adam Barry Feder

IPC: H04N23/67 ,  H04N5/265 ,  H04N23/45 ,  H04N23/51 ,  H04N23/54 ,  H04N23/55 ,  H04N23/56 ,  H04N23/57 ,  H04N23/60 ,  H04N23/611 ,  H04N23/62 ,  H04N23/743 ,  H04N23/951

CPC classification number: H04N23/67 ,  H04N5/265 ,  H04N23/45 ,  H04N23/51 ,  H04N23/54 ,  H04N23/55 ,  H04N23/57 ,  H04N23/611 ,  H04N23/62 ,  H04N23/64 ,  H04N23/743 ,  H04N23/56 ,  H04N23/951

Abstract: A system, method, and computer program product are provided for generating a focus sweep to produce a focus stack. In use, an image is sampled as image data. Next, a first focus region is identified and a second focus region is identified. Next, first focus target information corresponding to the first focus region is determined and second focus target information corresponding to the second focus region is determined. Further, a focus is adjusted, based on the first focus target information and at least one first image is captured based on the first focus target information. Additionally, the focus is adjusted, based on the second focus target information and at least one second image is captured based on the second focus target information. Lastly, the at least one first image and the at least one second image are saved to an image stack. Additional systems, methods, and computer program products are also presented.

公开(公告)号：US11917301B2

公开(公告)日：2024-02-27

申请号：US17974966

申请日：2022-10-27

Applicant: CANON KABUSHIKI KAISHA

Inventor： Akimitsu Yoshida

IPC: H04N23/72 ,  H04N23/60 ,  H04N23/71 ,  H04N23/611 ,  H04N23/67 ,  H04N23/743

CPC classification number: H04N23/72 ,  H04N23/611 ,  H04N23/64 ,  H04N23/676 ,  H04N23/71 ,  H04N23/743

Abstract: An image capturing apparatus includes: an image capturing unit configured to control an imaging sensor; a first obtaining unit configured to obtain a first detection result that is a result of detection of a subject from image data captured by the image capturing unit; a second obtaining unit configured to transmit the image data to an external image processing apparatus and obtain a second detection result that is a result of detection of a subject from the image data by the image processing apparatus; and a control unit configured to perform shooting processing using settings of shooting parameters determined based on at least one of the first detection result and the second detection result, wherein the control unit is configured to perform shooting processing using settings of the shooting parameters determined based on the first detection result until the second detection result is obtained from the image processing apparatus.

公开(公告)号：US11843867B2

公开(公告)日：2023-12-12

申请号：US17817310

申请日：2022-08-03

Applicant: CANON KABUSHIKI KAISHA

Inventor： Ryo Shiota

IPC: H04N23/72 ,  H04N23/56 ,  H04N23/71 ,  H04N23/743

CPC classification number: H04N23/72 ,  H04N23/56 ,  H04N23/71 ,  H04N23/743

Abstract: An apparatus includes an image sensor configured to capture a plurality of images different in in-focus position, at least one memory configured to store instructions, and at least one processor in communication with the at least one memory and configured to execute the instructions to determine a predetermined value of exposure in advance, control exposure so that the image sensor captures the plurality of images with the exposure less than the predetermined value, and correct brightness of at least a part of the plurality of images based on the predetermined value.

公开(公告)号：US11758279B2

公开(公告)日：2023-09-12

申请号：US17213286

申请日：2021-03-26

Applicant: Texas Instruments Incorporated

Inventor： Mayank Mangla ,  Shashank Dabral ,  Peter Labaziewicz

IPC: H04N5/235 ,  H01L27/146 ,  H04N23/741 ,  G06T5/50 ,  H04N23/56 ,  H04N23/74 ,  H04N23/743 ,  H04N23/745

CPC classification number: H04N23/741 ,  G06T5/50 ,  H04N23/56 ,  H04N23/74 ,  H04N23/743 ,  H04N23/745 ,  G06T2207/10144 ,  G06T2207/20208

Abstract: A method of WDR imaging. Exposure times (ETs) are set for first and second frames for an image sensor to avoid second frame saturating by setting a second ET>1/a PWM frequency applied to an LED illuminating a scene to generate second longer ET pixel data (PD). The first frame has first PD and a first ET

公开(公告)号：US11722784B2

公开(公告)日：2023-08-08

申请号：US17834558

申请日：2022-06-07

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Yoshiaki Satou ,  Yasuo Miyake ,  Yasunori Inoue ,  Tokuhiko Tamaki

IPC: H04N23/743 ,  H04N25/53 ,  H04N25/534 ,  H04N25/57 ,  H04N25/587 ,  H04N25/59 ,  H04N25/70 ,  H04N25/76 ,  H01L27/146 ,  H04N5/262 ,  H04N23/62 ,  H04N23/10 ,  H04N23/73 ,  G03B7/08 ,  H04N23/63

CPC classification number: H04N23/743 ,  G03B7/08 ,  H04N23/10 ,  H04N23/73 ,  H04N25/53 ,  H04N25/534 ,  H04N25/57 ,  H04N25/587 ,  H04N25/59 ,  H04N25/70 ,  H04N25/76 ,  H01L27/14632 ,  H04N5/2621 ,  H04N23/631

Abstract: An imaging device including pixels and processing circuitry, where the pixels capture a first image in a first exposure period within a frame period and capture a second image in a second exposure period within the frame period to generate multiple-exposure image data that include the first image and the second image in a multiplexed state, the second exposure period being different from the first exposure period, the second image being different from the first image in brightness or color, and the processing circuitry detects an image of a moving subject from the multiple-exposure image data.

公开(公告)号：US20230206413A1

公开(公告)日：2023-06-29

申请号：US18178875

申请日：2023-03-06

Applicant: SPECTRAL MD, INC.

Inventor： Brian McCall ,  Wensheng Fan ,  Jason Dwight ,  Zhicun Gao ,  Jeffrey E. Thatcher ,  John Michael DiMaio

IPC: G06T5/50 ,  G06T7/55 ,  G06T7/62 ,  G06T7/33 ,  G06T7/00 ,  H04N5/265 ,  H04N23/55 ,  H04N23/56 ,  H04N23/743

CPC classification number: G06T5/50 ,  G06T7/55 ,  G06T7/62 ,  G06T7/33 ,  G06T7/0012 ,  H04N5/265 ,  H04N23/55 ,  H04N23/56 ,  H04N23/743 ,  G06T2207/10036 ,  G06T2207/10144 ,  G06T2207/20221

Abstract: Generally described, one or more aspects of the present application correspond to systems and techniques for spectral imaging using a multi-aperture system with curved multi-bandpass filters positioned over each aperture. The present disclosure further relates to techniques for implementing spectral unmixing and image registration to generate a spectral datacube using image information received from such imaging systems. Aspects of the present disclosure relate to using such a datacube to analyze the imaged object, for example to analyze tissue in a clinical setting, perform biometric recognition, or perform materials analysis.

公开(公告)号：US20250030945A1

公开(公告)日：2025-01-23

申请号：US18646620

申请日：2024-04-25

Applicant: Duelight LLC

Inventor： William Guie Rivard ,  Brian J. Kindle ,  Adam Barry Feder

IPC: H04N23/67 ,  H04N5/265 ,  H04N23/45 ,  H04N23/51 ,  H04N23/54 ,  H04N23/55 ,  H04N23/56 ,  H04N23/57 ,  H04N23/60 ,  H04N23/611 ,  H04N23/62 ,  H04N23/743 ,  H04N23/951

Abstract: A system, method, and computer program product are provided for generating a focus sweep to produce a focus stack. In use, an image is sampled as image data. Next, a first focus region is identified and a second focus region is identified. Next, first focus target information corresponding to the first focus region is determined and second focus target information corresponding to the second focus region is determined. Further, a focus is adjusted, based on the first focus target information and at least one first image is captured based on the first focus target information. Additionally, the focus is adjusted, based on the second focus target information and at least one second image is captured based on the second focus target information. Lastly, the at least one first image and the at least one second image are saved to an image stack. Additional systems, methods, and computer program products are also presented.